Object-based detection of vehicles using combined optical and elevation data
| Autor: | Dimitri Bulatov, Wolfgang Middelmann, Hendrik Schilling |
|---|---|
| Přispěvatelé: | Publica |
| Rok vydání: | 2018 |
| Předmět: |
Computer science
Feature extraction 0211 other engineering and technologies 02 engineering and technology high-resolution Convolutional neural network elevation data 0202 electrical engineering electronic engineering information engineering object-based classification Computers in Earth Sciences Vehicle detection Engineering (miscellaneous) 021101 geological & geomatics engineering data fusion business.industry feature extraction Pattern recognition Sensor fusion Atomic and Molecular Physics and Optics Computer Science Applications Random forest Identification (information) Workflow 020201 artificial intelligence & image processing Artificial intelligence State (computer science) business F1 score random forest cluster analysis |
| Zdroj: | ISPRS Journal of Photogrammetry and Remote Sensing. 136:85-105 |
| ISSN: | 0924-2716 |
| DOI: | 10.1016/j.isprsjprs.2017.11.023 |
| Popis: | The detection of vehicles is an important and challenging topic that is relevant for many applications. In this work, we present a workflow that utilizes optical and elevation data to detect vehicles in remotely sensed urban data. This workflow consists of three consecutive stages: candidate identification, classification, and single vehicle extraction. Unlike in most previous approaches, fusion of both data sources is strongly pursued at all stages. While the first stage utilizes the fact that most man-made objects are rectangular in shape, the second and third stages employ machine learning techniques combined with specific features. The stages are designed to handle multiple sensor input, which results in a significant improvement. A detailed evaluation shows the benefits of our workflow, which includes hand-tailored features; even in comparison with classification approaches based on Convolutional Neural Networks, which are state of the art in computer vision, we could obtain a comparable or superior performance (F1 score of 0.96–0.94). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect